PcLast: Discovering Plannable Continuous Latent States

• URL: http://arxiv.org/abs/2311.03534v2
• Date: Tue, 11 Jun 2024 03:32:58 GMT
• Title: PcLast: Discovering Plannable Continuous Latent States
• Authors: Anurag Koul, Shivakanth Sujit, Shaoru Chen, Ben Evans, Lili Wu, Byron Xu, Rajan Chari, Riashat Islam, Raihan Seraj, Yonathan Efroni, Lekan Molu, Miro Dudik, John Langford, Alex Lamb,
• Abstract summary: We learn a representation that associates reachable states together for effective planning and goal-conditioned policy learning. Our proposals are rigorously tested in various simulation testbeds.
• Score: 24.78767380808056
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision making, they ignore state reachability, hampering their performance. In this paper, we learn a representation that associates reachable states together for effective planning and goal-conditioned policy learning. We first learn a latent representation with multi-step inverse dynamics (to remove distracting information), and then transform this representation to associate reachable states together in $\ell_2$ space. Our proposals are rigorously tested in various simulation testbeds. Numerical results in reward-based settings show significant improvements in sampling efficiency. Further, in reward-free settings this approach yields layered state abstractions that enable computationally efficient hierarchical planning for reaching ad hoc goals with zero additional samples.

Related papers

• Learning Policy Representations for Steerable Behavior Synthesis [80.4542176039074]
  Given a Markov decision process (MDP), we seek to learn representations for a range of policies to facilitate behavior steering at test time.<n>We show that these representations can be approximated uniformly for a range of policies using a set-based architecture.<n>We use variational generative approach to induce a smooth latent space, and further shape it with contrastive learning so that latent distances align with differences in value functions.
  arXiv  Detail & Related papers  (2026-01-29T21:52:06Z)
• When Object-Centric World Models Meet Policy Learning: From Pixels to Policies, and Where It Breaks [24.669692812050645]
  We introduce a fully unsupervised, disentangled object-centric world model that learns object-level latents directly from pixels.<n>DLPWM achieves strong reconstruction and prediction performance, including robustness to several out-of-distribution (OOD) visual variations.<n>Our results suggest that, although object-centric perception supports robust visual modeling, achieving stable control requires mitigating latent drift.
  arXiv  Detail & Related papers  (2025-11-08T21:09:44Z)
• Dual Goal Representations [57.43956630070019]
  We introduce dual goal representations for goal-conditioned reinforcement learning (GCRL)<n>A dual goal representation characterizes a state by "the set of temporal distances from all other states"<n>We empirically show that dual goal representations consistently improve offline goal-reaching performance across 20 state- and pixel-based tasks.
  arXiv  Detail & Related papers  (2025-10-08T07:07:39Z)
• Improving Large Language Model Planning with Action Sequence Similarity [50.52049888490524]
  In this work, we explore how to improve the model planning capability through in-context learning (ICL)<n>We propose GRASE-DC: a two-stage pipeline that first re-samples high AS exemplars and then curates the selected exemplars.<n>Our experimental result confirms that GRASE-DC achieves significant performance improvement on various planning tasks.
  arXiv  Detail & Related papers  (2025-05-02T05:16:17Z)
• Latent Diffusion Planning for Imitation Learning [78.56207566743154]
  Latent Diffusion Planning (LDP) is a modular approach consisting of a planner and inverse dynamics model. By separating planning from action prediction, LDP can benefit from the denser supervision signals of suboptimal and action-free data. On simulated visual robotic manipulation tasks, LDP outperforms state-of-the-art imitation learning approaches.
  arXiv  Detail & Related papers  (2025-04-23T17:53:34Z)
• ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning [90.41852663775086]
  ACT-JEPA is a novel architecture that integrates imitation learning and self-supervised learning. We train a policy to predict action sequences and abstract observation sequences. Our experiments show that ACT-JEPA improves the quality of representations by learning temporal environment dynamics.
  arXiv  Detail & Related papers  (2025-01-24T16:41:41Z)
• Bidirectional Decoding: Improving Action Chunking via Closed-Loop Resampling [51.38330727868982]
  Bidirectional Decoding (BID) is a test-time inference algorithm that bridges action chunking with closed-loop operations. We show that BID boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks.
  arXiv  Detail & Related papers  (2024-08-30T15:39:34Z)
• Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policies [25.760946763103483]
  We propose Imagination Policy, a novel multi-task key-frame policy network for solving high-precision pick and place tasks. Instead of learning actions directly, Imagination Policy generates point clouds to imagine desired states which are then translated to actions using rigid action estimation.
  arXiv  Detail & Related papers  (2024-06-17T17:00:41Z)
• Hierarchical State Abstraction Based on Structural Information Principles [70.24495170921075]
  We propose a novel mathematical Structural Information principles-based State Abstraction framework, namely SISA, from the information-theoretic perspective. SISA is a general framework that can be flexibly integrated with different representation-learning objectives to improve their performances further.
  arXiv  Detail & Related papers  (2023-04-24T11:06:52Z)
• PALMER: Perception-Action Loop with Memory for Long-Horizon Planning [1.5469452301122177]
  We introduce a general-purpose planning algorithm called PALMER. Palmer combines classical sampling-based planning algorithms with learning-based perceptual representations. This creates a tight feedback loop between representation learning, memory, reinforcement learning, and sampling-based planning.
  arXiv  Detail & Related papers  (2022-12-08T22:11:49Z)
• Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning [105.70602423944148]
  We propose a novel method, called value-consistent representation learning (VCR), to learn representations that are directly related to decision-making. Instead of aligning this imagined state with a real state returned by the environment, VCR applies a $Q$-value head on both states and obtains two distributions of action values. It has been demonstrated that our methods achieve new state-of-the-art performance for search-free RL algorithms.
  arXiv  Detail & Related papers  (2022-06-25T03:02:25Z)
• Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metrics [1.5293427903448022]
  Deep Reinforcement Learning has shown its ability in solving complicated problems directly from high-dimensional observations. In end-to-end settings, Reinforcement Learning algorithms are not sample-efficient and requires long training times and quantities of data. We propose a framework for sample-efficient Reinforcement Learning that take advantage of state and action representations to transform a high-dimensional problem into a low-dimensional one.
  arXiv  Detail & Related papers  (2021-07-04T16:26:04Z)
• Provable Representation Learning for Imitation with Contrastive Fourier Features [27.74988221252854]
  We consider using offline experience datasets to learn low-dimensional state representations. A central challenge is that the unknown target policy itself may not exhibit low-dimensional behavior. We derive a representation learning objective which provides an upper bound on the performance difference between the target policy and a lowdimensional policy trained with max-likelihood.
  arXiv  Detail & Related papers  (2021-05-26T00:31:30Z)
• Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic [59.94347858883343]
  This paper investigates the motion planning of autonomous dynamical systems modeled by Markov decision processes (MDP) The novelty is to design an embedded product MDP (EP-MDP) between the LDGBA and the MDP. The proposed LDGBA-based reward shaping and discounting schemes for the model-free reinforcement learning (RL) only depend on the EP-MDP states.
  arXiv  Detail & Related papers  (2021-02-24T01:11:25Z)
• SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization [52.20602782690776]
  It is expensive and tedious to obtain large scale paired sparse-canned point sets for training from real scanned sparse data. We propose a self-supervised point cloud upsampling network, named SPU-Net, to capture the inherent upsampling patterns of points lying on the underlying object surface. We conduct various experiments on both synthetic and real-scanned datasets, and the results demonstrate that we achieve comparable performance to the state-of-the-art supervised methods.
  arXiv  Detail & Related papers  (2020-12-08T14:14:09Z)
• Automated Concatenation of Embeddings for Structured Prediction [75.44925576268052]
  We propose Automated Concatenation of Embeddings (ACE) to automate the process of finding better concatenations of embeddings for structured prediction tasks. We follow strategies in reinforcement learning to optimize the parameters of the controller and compute the reward based on the accuracy of a task model.
  arXiv  Detail & Related papers  (2020-10-10T14:03:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.